1. 说明
本文档针对docker swarm操作。
针对的系统是以一个本地的测试系统为例。其中机器信息如下，172.16.1.13作为docker swarm的管理机。
本地测试的机器列表信息：
| 主机名 | 模拟的外网 | 内网IP | 要部署模块 |
|---|---|---|---|
| mini01 | 10.0.0.11 | 172.16.1.11 | tomcat、hadoop-datanode、hbase-regionserver |
| mini02 | 10.0.0.12 | 172.16.1.12 | tomcat、hadoop-datanode、hbase-regionserver |
| mini03 | 10.0.0.13 | 172.16.1.13 | spark、zookeeper、hadoop-namnode、hbase-master、visualizer【docker swarm 状态查看】 |
2. docker swarm初始化
根据规划在172.16.1.13这台机器上操作：
[root@mini03 ~]# docker swarm init # 针对机器只有一个IP的情况
Error response from daemon: could not choose an IP address to advertise since this system has multiple addresses on different interfaces (172.16.1.13 on eth0 and 10.0.0.13 on eth1) - specify one with --advertise-addr
[root@mini03 ~]# docker swarm init --advertise-addr 172.16.1.13 # 针对机器有多个IP的情况，需要指定一个IP，一般都是指定内网IP
Swarm initialized: current node (yo5f7qb28gf6g38ve4xhcis17) is now a manager.
To add a worker to this swarm, run the following command:
# 在其他机器上执行，这样可以加入该swarm管理
docker swarm join --token SWMTKN-1-4929ovxh6agko49u0yokrzustjf6yzt30iv1zvwqn8d3pndm92-0kuha3sa80u2u27yca6kzdbnb 172.16.1.13:2377
To add a manager to this swarm, run 'docker swarm join-token manager' and follow the instructions.
得到加入到该swarm的命令
[root@mini03 ~]# docker swarm join-token worker
To add a worker to this swarm, run the following command:
# 在其他机器上执行，这样可以加入该swarm管理
docker swarm join --token SWMTKN-1-4929ovxh6agko49u0yokrzustjf6yzt30iv1zvwqn8d3pndm92-0kuha3sa80u2u27yca6kzdbnb 172.16.1.13:2377
3. 初始化网络
初始化一个swarm网络，让系统组件使用这个指定的网络。
[root@mini03 ~]# docker network create -d overlay --attachable zhang
vu07em5fvpuojih6wgckdkdzj
[root@mini03 docker-swarm]# docker network ls # 查看网络
NETWORK ID NAME DRIVER SCOPE
fa8a244c6bd5 bridge bridge local
51c95dea1e5c docker_gwbridge bridge local
7a7e31f4bce8 host host local
5hgg372xwxbl ingress overlay swarm
lmt3pjswf7l0 zhang overlay swarm
5ea08e9a282f none null local
[root@mini03 ~]# docker network inspect zhang # 查看网络信息
[
{
"Name": "zhang",
"Id": "xiykborz8hn2td40ykhi20dck",
"Created": "0001-01-01T00:00:00Z",
"Scope": "swarm",
"Driver": "overlay",
"EnableIPv6": false,
"IPAM": {
"Driver": "default",
"Options": null,
"Config": []
},
"Internal": false,
"Attachable": true,
"Ingress": false,
"ConfigFrom": {
"Network": ""
},
"ConfigOnly": false,
"Containers": null,
"Options": {
"com.docker.network.driver.overlay.vxlanid_list": "4097"
},
"Labels": null
}
]
删除网络【慎用】
删除docker中的zhang网络
[root@mini03 docker-swarm]# docker network rm zhang
zhang
[root@mini03 docker-swarm]# docker network ls
NETWORK ID NAME DRIVER SCOPE
fa8a244c6bd5 bridge bridge local
51c95dea1e5c docker_gwbridge bridge local
7a7e31f4bce8 host host local
5hgg372xwxbl ingress overlay swarm
5ea08e9a282f none null local
4. 加入或退出swarm管理
在mini01、mini02上执行如下命令：
docker swarm join --token SWMTKN-1-4929ovxh6agko49u0yokrzustjf6yzt30iv1zvwqn8d3pndm92-0kuha3sa80u2u27yca6kzdbnb 172.16.1.13:2377
4.1. 当前swarm有哪些节点
[root@mini03 ~]# docker node ls
ID HOSTNAME STATUS AVAILABILITY MANAGER STATUS ENGINE VERSION
2pfwllgxpajx5aitlvcih9vsq mini01 Ready Active 17.09.0-ce
zho14u85itt5l2i6cpg8fcd6t mini02 Ready Active 17.09.0-ce
yo5f7qb28gf6g38ve4xhcis17 * mini03 Ready Active Leader 17.09.0-ce
4.2. 退出当前的swarm节点
# 在swarm管理机mini03上的操作
# 其中 2pfwllgxpajx5aitlvcih9vsq 是mini01在swarm机器上的ID，根据docker node ls 获取
[root@mini03 ~]# docker node rm --force 2pfwllgxpajx5aitlvcih9vsq # 如果mini01上的docker没有停止服务，那么就需要使用 --force 选项
2pfwllgxpajx5aitlvcih9vsq
[root@mini03 ~]# docker node ls
ID HOSTNAME STATUS AVAILABILITY MANAGER STATUS ENGINE VERSION
zho14u85itt5l2i6cpg8fcd6t mini02 Ready Active 17.09.0-ce
yo5f7qb28gf6g38ve4xhcis17 * mini03 Ready Active Leader 17.09.0-ce
##########################################
# 需要在mini01上执行的命令，这样mini01才能彻底退出swarm管理
[root@mini01 ~]# docker swarm leave
Node left the swarm.
4.3. swarm管理机退出swarm
首先需要删除所有节点，然后强制退出swarm即可
[root@mini03 ~]# docker node ls
ID HOSTNAME STATUS AVAILABILITY MANAGER STATUS ENGINE VERSION
yo5f7qb28gf6g38ve4xhcis17 * mini03 Ready Active Leader 17.09.0-ce
[root@mini03 ~]# docker swarm leave --force # swarm管理机退出swarm，需要 --force 参数
Node left the swarm.
[root@mini03 ~]# docker node ls
Error response from daemon: This node is not a swarm manager. Use "docker swarm init" or "docker swarm join" to connect this node to swarm and try again.
4.4. 当前swarm有哪些服务
[root@mini03 ~]# docker service ls # 只是示例，不是实际数据
ID NAME MODE REPLICAS IMAGE PORTS
lq7zkkal6ujt hadoop_datanode global 2/2 bde2020/hadoop-datanode:2.0.0-hadoop2.7.4-java8
ph2fu37k886b hadoop_namenode replicated 1/1 bde2020/hadoop-namenode:2.0.0-hadoop2.7.4-java8 *:50070->50070/tcp
ca47u5i2ubes hbase-master replicated 1/1 bde2020/hbase-master:1.0.0-hbase1.2.6 *:16010->16010/tcp
mkks4oa2ppcn hbase-regionserver-1 replicated 1/1 bde2020/hbase-regionserver:1.0.0-hbase1.2.6
j4mhizg4j67p hbase-regionserver-2 replicated 1/1 bde2020/hbase-regionserver:1.0.0-hbase1.2.6
yndrkc2bcpra hbase_zoo1 replicated 1/1 zookeeper:3.4.10 *:2181->2181/tcp
r5ycrvo0zout spark_spark replicated 1/1 zhang/spark:latest *:4040->4040/tcp,*:7777->7777/tcp,*:8081->8081/tcp,*:18080->8080/tcp
f2v091nz24rg tomcat_tomcat global 2/2 zhang/tomcat:latest *:6543->6543/tcp,*:9999->9999/tcp,*:18081->8081/tcp
clfpryaerq2l visualizer replicated 1/1 dockersamples/visualizer:latest *:8080->8080/tcp
5. swarm标签管理
5.1. 标签添加
根据最开始的主机和组件部署规划，标签规划如下：在swarm管理机mini03上执行。
# 给mini01机器的标签
docker node update --label-add tomcat=true mini01
docker node update --label-add datanode=true mini01
docker node update --label-add hbase-regionserver-1=true mini01
# 给mini02机器的标签
docker node update --label-add tomcat=true mini02
docker node update --label-add datanode=true mini02
docker node update --label-add hbase-regionserver-2=true mini02
# 给mini03机器的标签
docker node update --label-add spark=true mini03
docker node update --label-add zookeeper=true mini03
docker node update --label-add namenode=true mini03
docker node update --label-add hbase-master=true mini03
5.2. 删除标签
在swarm管理机mini03上执行，示例如下：
docker node update --label-rm zookeeper mini03
5.3. 查看swarm当前的标签
在swarm管理机mini03上执行：
[root@mini03 ~]# docker node ls -q | xargs docker node inspect -f '{{.ID}}[{{.Description.Hostname}}]:{{.Spec.Labels}}'
6f7dwt47y6qvgs3yc6l00nmjd[mini01]:map[tomcat:true datanode:true hbase-regionserver-1:true]
5q2nmm2xaexhkn20z8f8ezglr[mini02]:map[tomcat:true datanode:true hbase-regionserver-2:true]
ncppwjknhcwbegmliafut0718[mini03]:map[hbase-master:true namenode:true spark:true zookeeper:true]
6. 查看日志
启动容器时，查看相关日志，例如如下：
docker stack ps hadoop
docker stack ps hadoop --format "{{.Name}}: {{.Error}}"
docker stack ps hadoop --format "{{.Name}}: {{.Error}}" --no-trunc
docker stack ps hadoop --no-trunc